INDEX

Explanations

numerical values within a specific range, potentially related to statistics or measurements

oai_token-act-pair · gpt-3.5-turbo

numerical statistics and data points

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

umbn

-0.84

rament

-0.76

raltar

-0.74

rises

-0.73

unders

-0.71

rays

-0.71

idays

-0.70

pty

-0.69

ainted

-0.68

awaru

-0.67

POSITIVE LOGITS

 WRITE

0.97

ERA

0.80

ly

0.77

0.76

#$

0.72

GPA

0.70

 msec

0.69

GHz

0.67

 lakh

0.66

Activations Density 0.057%

numerical values within a specific range, potentially related to statistics or measurements

numerical statistics and data points

No Comments

No Known Activations