INDEX

Explanations

words related to non-combat activities

oai_token-act-pair · gpt-3.5-turbo

terms associated with non-combat related contexts across various categories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ravings

-0.69

 anew

-0.65

Hope

-0.64

endas

-0.63

Dialogue

-0.61

Ev

-0.61

QUIRE

-0.59

Attack

-0.59

ramids

-0.59

BALL

-0.59

POSITIVE LOGITS

theless

0.95

oidal

0.94

ensical

0.94

ailable

0.87

restrial

0.87

izable

0.87

animous

0.83

existent

0.82

ensable

0.82

igenous

0.82

Activations Density 0.110%

words related to non-combat activities

terms associated with non-combat related contexts across various categories

No Comments

No Known Activations