INDEX

Explanations

phrases related to news events or mentions of specific locations or years

oai_token-act-pair · gpt-3.5-turbo

specific locations and references to time and circumstance

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

yond

-0.57

true

-0.56

'.

-0.55

$.

-0.55

pac

-0.54

Advertisements

-0.54

clusively

-0.52

soType

-0.52

atever

-0.51

 Surviv

-0.51

POSITIVE LOGITS

 consisted

1.05

 consists

0.98

 seemed

0.98

 fared

0.95

 refers

0.91

 seems

0.91

 appears

0.88

 grew

0.87

 reacted

0.86

 belonged

0.86

Activations Density 0.353%

phrases related to news events or mentions of specific locations or years

specific locations and references to time and circumstance

No Comments

No Known Activations