INDEX

Explanations

countries or locations

oai_token-act-pair · gpt-3.5-turbo

references to specific countries and locations

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

NUM

-0.64

 disagreement

-0.62

 resemblance

-0.62

Rating

-0.62

 replay

-0.61

NUM

-0.60

aneous

-0.59

 severity

-0.58

 precedence

-0.58

 repetition

-0.58

POSITIVE LOGITS

via

0.93

 shores

0.82

 undet

0.81

 illegally

0.81

 destinations

0.81

 unaccompanied

0.74

 fray

0.72

agar

0.71

 beck

0.71

 ASAP

0.70

Activations Density 0.286%

countries or locations

references to specific countries and locations

No Comments

No Known Activations