INDEX

Explanations

phrases related to repeated actions or events

oai_token-act-pair · gpt-3.5-turbo

the concept of repetition 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 @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

emed

-0.78

istry

-0.76

wit

-0.75

sie

-0.75

istics

-0.74

emen

-0.71

ramid

-0.71

istical

-0.70

ovies

-0.70

hest

-0.70

POSITIVE LOGITS

 repeats

0.98

 repetition

0.97

 repeating

0.91

 repeated

0.89

 repeat

0.85

 occurrences

0.84

 rounds

0.82

 offenders

0.81

 assurances

0.80

 playthrough

0.80

Activations Density 0.016%

phrases related to repeated actions or events

the concept of repetition in various contexts

No Comments

No Known Activations