INDEX

Explanations

references to a specific news agency, "The Associated Press"

oai_token-act-pair · gpt-3.5-turbo

references to the Associated Press

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

gone

-0.98

orously

-0.90

stood

-0.79

wagen

-0.77

warm

-0.77

vae

-0.77

ggle

-0.74

oglu

-0.74

etime

-0.73

gart

-0.73

POSITIVE LOGITS

 Newsp

0.97

 Press

0.85

 Colleg

0.85

 Arbit

0.84

 Tribune

0.82

 States

0.78

Journal

0.78

 Cooperative

0.77

 Association

0.77

 Corporation

0.75

Activations Density 0.009%

references to a specific news agency, "The Associated Press"

references to the Associated Press

No Comments

No Known Activations