INDEX

Explanations

mentions of various types of people or characters in different situations and contexts

oai_token-act-pair · gpt-3.5-turbo

references to character struggles and conflicts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

enhagen

-0.74

nces

-0.73

outube

-0.72

uly

-0.72

andum

-0.70

osaurus

-0.70

 congrat

-0.68

ety

-0.68

otos

-0.65

wagon

-0.65

POSITIVE LOGITS

 thriller

0.93

Untitled

0.89

Director

0.81

é¾

0.80

Haunted

0.79

Male

0.78

Fear

0.78

 novelist

0.77

0.76

Rating

0.76

Activations Density 0.065%

mentions of various types of people or characters in different situations and contexts

references to character struggles and conflicts

No Comments

No Known Activations