INDEX

Explanations

repeated actions or events

oai_token-act-pair · gpt-3.5-turbo

instances of the word "repeated."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

emen

-0.85

hov

-0.77

istry

-0.76

hest

-0.75

sie

-0.75

istics

-0.75

wit

-0.74

istical

-0.72

ampunk

-0.72

topia

-0.72

POSITIVE LOGITS

 repetition

1.18

 repeats

1.11

 repeated

1.09

 repeating

1.04

 repeat

0.97

 occurrences

0.96

 repet

0.92

 subsequ

0.88

 assurances

0.85

 reiter

0.84

Activations Density 0.011%

repeated actions or events

instances of the word "repeated."

No Comments

No Known Activations