INDEX

Explanations

words related to conversation and discussion

oai_token-act-pair · gpt-3.5-turbo

discussions surrounding social interactions and relationships

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

 policymakers

-0.60

 administr

-0.59

 relying

-0.57

 analysts

-0.54

 broadly

-0.54

 economically

-0.53

 reliance

-0.52

 economic

-0.52

 analysis

-0.50

 incumbent

-0.50

POSITIVE LOGITS

 fucking

0.82

 FUCK

0.80

fuck

0.77

 fuckin

0.76

 shit

0.76

 shitty

0.75

HAHAHAHA

0.73

 goddamn

0.72

 fuck

0.71

 Fuck

0.71

Activations Density 2.561%

words related to conversation and discussion

discussions surrounding social interactions and relationships

No Comments

No Known Activations