INDEX

Explanations

historical or past references

oai_token-act-pair · gpt-3.5-turbo

references to historical context or significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ity

-0.69

ovich

-0.69

 Stuff

-0.66

anim

-0.65

stuff

-0.64

Pages

-0.63

 Sahara

-0.63

Eva

-0.61

 Extensions

-0.61

plan

-0.61

POSITIVE LOGITS

ãĤ©

0.88

 relied

0.85

 represented

0.82

 conduc

0.81

 belonged

0.77

 speaking

0.77

 housed

0.76

 incapable

0.76

 positioned

0.75

 regarded

0.75

Activations Density 0.084%

historical or past references

references to historical context or significance

No Comments

No Known Activations