INDEX

Explanations

terms related to technology and data processing

oai_token-act-pair · gpt-3.5-turbo

terms related to health, social issues, and biases

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å§«

-0.79

upper

-0.77

hess

-0.75

JM

-0.74

psons

-0.73

hene

-0.69

etsk

-0.68

 Canaver

-0.68

bard

-0.67

daq

-0.65

POSITIVE LOGITS

etc

0.90

cellaneous

0.76

 activities

0.75

 disturbances

0.72

 therapies

0.69

 enrichment

0.69

 retention

0.69

 accessibility

0.68

 adjustments

0.68

 counseling

0.68

Activations Density 0.425%

terms related to technology and data processing

terms related to health, social issues, and biases

No Comments

No Known Activations