INDEX

Explanations

references to geographical locations

oai_token-act-pair · gpt-3.5-turbo

references to "British" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

mble

-0.90

ographed

-0.75

pty

-0.75

efer

-0.74

ovie

-0.73

ologies

-0.73

regation

-0.73

eger

-0.72

icago

-0.69

neapolis

-0.69

POSITIVE LOGITS

 Isles

1.45

 Columb

1.38

 Columbia

1.37

 Airways

1.23

 Virgin

0.97

 Overse

0.92

 Parliament

0.91

 Antarctic

0.90

 Telecom

0.85

 tabl

0.82

Activations Density 0.035%

references to geographical locations

references to "British" in various contexts

No Comments

No Known Activations