INDEX

Explanations

contradictions in statements

oai_token-act-pair · gpt-3.5-turbo

present tense and past tense forms of the verb "to be"

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

doms

-0.90

ESE

-0.81

osate

-0.72

ievers

-0.72

glers

-0.71

Edit

-0.68

IFE

-0.67

wake

-0.65

inav

-0.65

Congratulations

-0.65

POSITIVE LOGITS

 worth

0.86

 meant

0.85

 certainly

0.82

 also

0.80

 downright

0.79

 nonetheless

0.79

 necessary

0.75

nt

0.75

 inevitable

0.75

 achievable

0.75

Activations Density 0.332%

contradictions in statements

present tense and past tense forms of the verb "to be"

No Comments

No Known Activations