INDEX

Explanations

references to future events or releases

oai_token-act-pair · gpt-3.5-turbo

references to something that is forthcoming or anticipated

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

orthodox

-0.76

ruff

-0.76

ricular

-0.76

claimer

-0.72

ording

-0.72

pelling

-0.72

bia

-0.71

uliffe

-0.71

oller

-0.71

acca

-0.71

POSITIVE LOGITS

 undone

1.12

 attractions

0.93

Soon

0.84

 apart

0.83

 together

0.82

 ashore

0.81

up

0.79

 closer

0.78

 into

0.76

 forth

0.76

Activations Density 0.038%

references to future events or releases

references to something that is forthcoming or anticipated

No Comments

No Known Activations