INDEX

Explanations

phrases related to disputed or debunked claims or rumors

oai_token-act-pair · gpt-3.5-turbo

the word "that" 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 @ 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

atre

-0.66

pling

-0.64

onomic

-0.61

 Pradesh

-0.59

 Gallery

-0.59

 Divinity

-0.58

ouk

-0.57

osures

-0.56

Eye

-0.55

ones

-0.55

POSITIVE LOGITS

 accompanies

1.14

 arose

0.95

 preceded

0.91

soever

0.86

©¶æ

0.85

 contradicts

0.82

 accompanied

0.81

 contradicted

0.78

 they

0.78

 governs

0.77

Activations Density 0.224%

phrases related to disputed or debunked claims or rumors

the word "that" in various contexts

No Comments

No Known Activations