INDEX

Explanations

words related to grouping, categorization, or connections between different concepts

oai_token-act-pair · gpt-3.5-turbo

terms related to associations and connections between concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

=-=-=-=-=-=-=-=-

-0.79

gm

-0.74

cale

-0.72

nl

-0.66

raq

-0.65

fare

-0.65

oÄŁ

-0.63

sets

-0.61

OUT

-0.60

stall

-0.60

POSITIVE LOGITS

 associations

0.98

eer

0.97

eering

0.93

ality

0.93

 affili

0.88

 association

0.86

esthesia

0.79

ually

0.78

eers

0.77

ally

0.75

Activations Density 0.030%

words related to grouping, categorization, or connections between different concepts

terms related to associations and connections between concepts

No Comments

No Known Activations