INDEX

Explanations

discussions about various influencing factors

oai_token-act-pair · gpt-3.5-turbo

mentions of various contributing factors in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

clean

-0.79

scribe

-0.78

ENSE

-0.70

DEM

-0.66

obook

-0.65

arium

-0.65

gard

-0.63

cious

-0.63

boro

-0.61

 Night

-0.61

POSITIVE LOGITS

 factors

3.66

 Factors

2.81

 factor

2.47

 variables

1.92

 considerations

1.82

factor

1.79

 Factor

1.67

Factor

1.62

 reasons

1.58

 influences

1.54

Activations Density 0.020%

discussions about various influencing factors

mentions of various contributing factors in different contexts

No Comments

No Known Activations