INDEX

Explanations

mentions of specific physical locations or sites

oai_token-act-pair · gpt-3.5-turbo

references to specific locations or sites

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ornia

-0.81

olyn

-0.79

sen

-0.73

icipated

-0.71

lass

-0.71

cia

-0.70

 Leilan

-0.70

thood

-0.69

atures

-0.67

ths

-0.65

POSITIVE LOGITS

 site

0.79

 Site

0.76

 sites

0.76

ologies

0.74

 location

0.74

 redevelopment

0.72

plan

0.70

builders

0.69

 locations

0.68

keeper

0.68

Activations Density 0.027%

mentions of specific physical locations or sites

references to specific locations or sites

No Comments

No Known Activations