INDEX

Explanations

statistics related to proportions or fractions

oai_token-act-pair · gpt-3.5-turbo

numerical data or statistics related to proportions and ratios in various contexts

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

jan

-0.67

har

-0.64

edd

-0.64

gang

-0.64

emb

-0.64

rev

-0.63

 ramp

-0.59

leans

-0.59

unct

-0.58

 Hassan

-0.58

POSITIVE LOGITS

 respondents

0.79

 Americans

0.73

(%

0.72

 households

0.69

ones

0.65

 overall

0.65

 earners

0.64

(%)

0.64

 cases

0.64

NPR

0.64

Activations Density 0.067%

statistics related to proportions or fractions

numerical data or statistics related to proportions and ratios in various contexts

No Comments

No Known Activations