INDEX

Explanations

I'm sorry, it seems like Neuron 4 did not show consistent activations to provide a clear summary. Let me know if you would like more assistance with this neuron or any other aspect

oai_token-act-pair · gpt-3.5-turbo

the phrase "Continue reading" in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ranch

-0.83

arse

-0.70

»Ĵ

-0.70

MpServer

-0.68

bid

-0.66

arious

-0.66

ĪĴ

-0.66

opic

-0.66

rador

-0.63

EStreamFrame

-0.63

POSITIVE LOGITS

 Continue

0.81

 Continued

0.80

 Loading

0.73

...]

0.71

chu

0.68

 Reading

0.68

taboola

0.67

 Transcript

0.66

 Advertisement

0.64

CLASSIFIED

0.64

Activations Density 0.012%

I'm sorry, it seems like Neuron 4 did not show consistent activations to provide a clear summary. Let me know if you would like more assistance with this neuron or any other aspect

the phrase "Continue reading" in various contexts

No Comments

No Known Activations