INDEX

Explanations

phrases related to evaluations, assessments, analyses, or investigations

oai_token-act-pair · gpt-3.5-turbo

mentions of reviews related to policies or assessments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 Hots

-0.70

Corn

-0.68

pox

-0.68

âĹ¼

-0.67

pots

-0.65

ITIES

-0.64

icz

-0.63

onne

-0.63

Beaut

-0.62

kt

-0.62

POSITIVE LOGITS

opian

0.97

 process

0.93

 judgment

0.80

spective

0.79

 judgement

0.79

 backlog

0.77

 hearings

0.75

rador

0.73

essee

0.72

 undertaken

0.72

Activations Density 0.026%

phrases related to evaluations, assessments, analyses, or investigations

mentions of reviews related to policies or assessments

No Comments

No Known Activations