INDEX

Explanations

phrases related to a specific individual or object

oai_token-act-pair · gpt-3.5-turbo

the article "a" in various contexts

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

Effects

-0.80

ATURES

-0.79

 Examples

-0.78

Examples

-0.77

iments

-0.76

orders

-0.74

uses

-0.74

arten

-0.73

results

-0.71

inson

-0.71

POSITIVE LOGITS

 deceased

0.92

 single

0.88

 defunct

0.87

 thousand

0.86

 lifetime

0.82

 nonexistent

0.81

 dozen

0.80

 nutshell

0.80

 fictitious

0.80

 hundred

0.79

Activations Density 0.178%

phrases related to a specific individual or object

the article "a" in various contexts

No Comments

No Known Activations