INDEX

Explanations

phrases related to attributing responsibility or blame

oai_token-act-pair · gpt-3.5-turbo

references to accountability and blame in context of actions and consequences

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

Tree

-0.79

isSpecialOrderable

-0.78

eki

-0.74

vine

-0.72

adj

-0.69

herer

-0.69

atories

-0.68

paces

-0.66

 Bake

-0.65

ibaba

-0.65

POSITIVE LOGITS

 sins

1.20

 sake

1.13

 inconvenience

1.08

 crimes

0.98

 transgress

0.95

 failings

0.90

 failures

0.88

 deaths

0.87

 offences

0.87

 mistakes

0.86

Activations Density 0.326%

phrases related to attributing responsibility or blame

references to accountability and blame in context of actions and consequences

No Comments

No Known Activations