INDEX

Explanations

negative sentiments or words

oai_token-act-pair · gpt-3.5-turbo

expressions or discussions related to negative thoughts and their impacts

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

DOM

-0.89

pread

-0.85

plain

-0.83

aido

-0.79

heet

-0.78

dropping

-0.78

olate

-0.76

ingham

-0.76

nington

-0.75

ISTORY

-0.75

POSITIVE LOGITS

 reinforcement

1.05

 impact

0.99

 gearing

0.96

 consequences

0.96

 spiral

0.95

 consequence

0.94

 impacts

0.92

 effects

0.92

 feedback

0.90

vib

0.90

Activations Density 0.041%

negative sentiments or words

expressions or discussions related to negative thoughts and their impacts

No Comments

No Known Activations