INDEX

Explanations

the word "Things" or similar variations

oai_token-act-pair · gpt-3.5-turbo

mentions of the concept of "things," particularly in relation to changes or situations

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

iary

-0.81

gee

-0.74

pless

-0.74

irst

-0.69

onym

-0.69

asio

-0.66

adia

-0.66

bern

-0.65

ILE

-0.64

NES

-0.63

POSITIVE LOGITS

 happened

1.09

 transpired

1.08

 happen

0.92

 happening

0.89

 Happ

0.88

 happens

0.86

 escalated

0.85

 happ

0.81

bably

0.80

 unfolded

0.79

Activations Density 0.039%

the word "Things" or similar variations

mentions of the concept of "things," particularly in relation to changes or situations

No Comments

No Known Activations