INDEX

Explanations

references to political positions or titles, specifically related to legislative bodies

oai_token-act-pair · gpt-3.5-turbo

references to a specific organization or group known as "ML."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

Pacific

-0.76

ylum

-0.71

oise

-0.66

rift

-0.66

 Portsmouth

-0.66

Prev

-0.65

 Pose

-0.65

Pac

-0.65

 Townsend

-0.64

lies

-0.63

POSITIVE LOGITS

ML

1.07

ML

0.88

ovember

0.88

arge

0.85

endon

0.85

CTV

0.82

andom

0.82

anguage

0.79

ibraries

0.78

NP

0.77

Activations Density 0.009%

references to political positions or titles, specifically related to legislative bodies

references to a specific organization or group known as "ML."

No Comments

No Known Activations