INDEX

Explanations

words related to negative events or situations

oai_token-act-pair · gpt-3.5-turbo

terms related to feelings of shame or social failure

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

 corrid

-0.80

ramer

-0.78

bors

-0.77

eways

-0.76

estone

-0.75

cium

-0.72

rame

-0.69

 Aires

-0.69

 livest

-0.68

nda

-0.68

POSITIVE LOGITS

 embarrassment

1.16

 certs

0.80

ously

0.75

è£ħ

0.75

èª

0.74

 dishon

0.73

ãĥĭ

0.73

é¾įå¥ĳå£«

0.73

UAL

0.72

lessly

0.72

Activations Density 0.015%

words related to negative events or situations

terms related to feelings of shame or social failure

No Comments

No Known Activations