INDEX

Explanations

years mentioned in time-related contexts

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "By" followed by numerical data or results

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

atem

-0.71

 pains

-0.64

SPONSORED

-0.63

ials

-0.63

abs

-0.63

ernal

-0.61

ptive

-0.61

ptions

-0.60

umble

-0.60

isable

-0.59

POSITIVE LOGITS

 contrast

1.23

 virtue

1.11

 implication

0.99

akuya

0.98

catch

0.96

 extension

0.84

 analogy

0.82

 sheer

0.81

pass

0.81

products

0.80

Activations Density 0.047%

years mentioned in time-related contexts

occurrences of the word "By" followed by numerical data or results

No Comments

No Known Activations