INDEX

Explanations

phrases indicating individual items or entities within a broader context

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Each"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

abs

-0.79

tops

-0.74

rovers

-0.73

haven

-0.72

dn

-0.69

duc

-0.68

Chain

-0.66

children

-0.66

ables

-0.65

stones

-0.65

POSITIVE LOGITS

 successive

1.19

 iteration

0.98

 individual

0.88

 participant

0.87

 person

0.84

where

0.83

 month

0.83

 piece

0.81

 member

0.80

 year

0.78

Activations Density 0.038%

phrases indicating individual items or entities within a broader context

occurrences of the word "Each"

No Comments

No Known Activations