INDEX

Explanations

words related to physical structures like walls

oai_token-act-pair · gpt-3.5-turbo

references to walls and related structures

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Gene

-0.84

phrine

-0.72

lihood

-0.71

Pacific

-0.69

Eug

-0.66

Wild

-0.66

 delegated

-0.65

orean

-0.64

MENTS

-0.64

milo

-0.63

POSITIVE LOGITS

papers

1.27

abies

1.19

aby

1.12

paper

1.00

clock

0.97

 thickness

0.92

 wall

0.89

 walls

0.87

 decoration

0.86

tops

0.85

Activations Density 0.030%

words related to physical structures like walls

references to walls and related structures

No Comments

No Known Activations