INDEX

Explanations

phrases related to significant events or changes

oai_token-act-pair · gpt-3.5-turbo

sentences that convey finality or conclusions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ascus

-0.77

hay

-0.72

 minim

-0.71

uer

-0.71

 equival

-0.69

ema

-0.67

 compr

-0.66

uly

-0.65

 behaviour

-0.65

 essence

-0.64

POSITIVE LOGITS

 Literally

1.07

 Dozens

1.02

Its

1.01

 Especially

0.99

 Located

0.98

 Whether

0.96

 Recall

0.94

 Sure

0.94

 Having

0.93

 Typically

0.92

Activations Density 0.460%

phrases related to significant events or changes

sentences that convey finality or conclusions

No Comments

No Known Activations