INDEX

Explanations

names and possibly keywords related to criminal cases or news events

oai_token-act-pair · gpt-3.5-turbo

names of individuals or proper nouns, particularly those with high activation values

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

essee

-0.72

ACTED

-0.72

Constructed

-0.70

ropri

-0.70

ffic

-0.69

NetMessage

-0.66

uncture

-0.65

ossession

-0.64

ventus

-0.64

 Sacrament

-0.64

POSITIVE LOGITS

renheit

1.08

Wah

1.04

Zah

0.99

ttp

0.94

awk

0.94

aji

0.94

rite

0.92

tml

0.89

ls

0.89

IJ

0.87

Activations Density 0.008%

names and possibly keywords related to criminal cases or news events

names of individuals or proper nouns, particularly those with high activation values

No Comments

No Known Activations