INDEX

Explanations

words related to approval or recognition

oai_token-act-pair · gpt-3.5-turbo

the repeated use of the prefix "comm-" across various contexts

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

 Elves

-0.65

wagen

-0.65

 vulgar

-0.64

loo

-0.59

Downloadha

-0.59

 dece

-0.59

 enriched

-0.56

 Divinity

-0.56

 contradictions

-0.55

ç¥ŀ

-0.54

POSITIVE LOGITS

encing

1.25

ences

1.11

itte

1.08

uted

1.07

mercial

0.97

utation

0.94

encer

0.94

enced

0.94

utations

0.93

ittal

0.92

Activations Density 0.014%

words related to approval or recognition

the repeated use of the prefix "comm-" across various contexts

No Comments

No Known Activations